Triple
T19983078
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Man Up |
E493864
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Sharon Horgan |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Sharon Horgan | Statement: [Man Up, castMember, Sharon Horgan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sharon Horgan Context triple: [Man Up, castMember, Sharon Horgan]
-
A.
Sharon Horgan
chosen
Sharon Horgan is an Irish writer, actress, comedian, and producer best known for creating and starring in acclaimed television comedies such as "Catastrophe" and "Bad Sisters."
-
B.
Michaela Coel
Michaela Coel is a British actress, screenwriter, director, and producer best known for creating and starring in the acclaimed series "Chewing Gum" and "I May Destroy You."
-
C.
Jill Soloway
Jill Soloway is an American writer, director, and producer known for their groundbreaking, queer and trans-inclusive storytelling in television and film.
-
D.
Miriam Heller
Miriam Heller is a notable individual bearing the surname Heller, recognized as a distinguished representative of the Heller family name.
-
E.
Olivia Waithe
Olivia Waithe is a writer best known for her work on the comedy special "What Now."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69da626a67648190af9653832a3aeced |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e65d14c3c08190b1ba8f4da08a4ccf |
completed | April 20, 2026, 5:06 p.m. |
Created at: April 11, 2026, 3:28 p.m.